Code
pacman::p_load(tidyverse, googledrive, bibliometrix, janitor, stringi,
summarytools)pacman::p_load(tidyverse, googledrive, bibliometrix, janitor, stringi,
summarytools)TITLE ( “pediatric” OR “paediatric” OR “childhood” OR “adolescent” OR “youth” ) AND TITLE ( “obesity” OR “obese” OR “overweight” ) AND PUBYEAR > 2003 AND PUBYEAR < 2024 AND ( LIMIT-TO ( DOCTYPE , “ar” ) ) AND ( LIMIT-TO ( PUBSTAGE , “final” ) ) AND ( LIMIT-TO ( SRCTYPE , “j” ) ) AND ( LIMIT-TO ( LANGUAGE , “English” ) )
pedob_bibds <- convert2df("250223_ScopusSearch.csv",
dbsource = "scopus",
format = "csv",
remove.duplicates = TRUE)
head(pedob_bibds)
write_rds(pedob_bibds, "pedob_bibds.rds")pedob_bibds <- read_rds("pedob_bibds.rds")dupti <- pedob_bibds %>%
count(TI, sort = T) %>%
filter(n > 1) %>%
pull(TI)
pedob_bibds %>%
arrange(TI, PY) %>%
filter(TI %in% dupti) %>%
mutate(ti_short = str_sub(TI, 1, 100), .before = 1)there was however several with same title.
pedob_bibds %>%
count(PY)pedob_bibds %>%
count(DT)pedob_bibres <- biblioAnalysis(pedob_bibds, sep = ";")
write_rds(pedob_bibres, "pedob_bibres.rds")pedob_bibres <- read_rds("pedob_bibres.rds")
summary(pedob_bibres)
MAIN INFORMATION ABOUT DATA
Timespan 1994 : 2023
Sources (Journals, Books, etc) 2444
Documents 12774
Annual Growth Rate % 13.56
Document Average Age 10.2
Average citations per doc 37.4
Average citations per year per doc 2.94
References 383117
DOCUMENT TYPES
article 12774
DOCUMENT CONTENTS
Keywords Plus (ID) 17898
Author's Keywords (DE) 11720
AUTHORS
Authors 44307
Author Appearances 80023
Authors of single-authored docs 563
AUTHORS COLLABORATION
Single-authored docs 637
Documents per Author 0.288
Co-Authors per Doc 6.26
International co-authorships % 19.45
Annual Scientific Production
Year Articles
1994 20
1995 30
1996 28
1997 37
1998 34
1999 51
2000 70
2001 100
2002 113
2003 118
2004 155
2005 209
2006 263
2007 308
2008 386
2009 462
2010 529
2011 599
2012 694
2013 740
2014 736
2015 736
2016 714
2017 763
2018 762
2019 798
2020 816
2021 828
2022 875
2023 800
Annual Percentage Growth Rate 13.56
Most Productive Authors
Authors Articles Authors Articles Fractionalized
1 WANG Y 104 WANG Y 20.44
2 CAPRIO S 98 CAPRIO S 16.65
3 THIVEL D 77 LEE S 15.64
4 MORENO LA 74 DANIELS SR 12.00
5 SARTORIO A 70 REINEHR T 10.84
6 DÂMASO AR 69 THIVEL D 10.36
7 TUFIK S 68 GORAN MI 10.12
8 REINEHR T 67 SARTORIO A 9.93
9 JR 65 STORY M 9.47
10 LEE S 64 BAUR LA 9.23
Top manuscripts per citations
Paper DOI TC TCperYear NTC
1 OGDEN CL, 2014, JAMA 10.1001/jama.2014.732 6699 558 161.0
2 BENTHAM J, 2017, LANCET 10.1016/S0140-6736(17)32129-3 5727 636 156.4
3 BARLOW SE, 2007, PEDIATRICS 10.1542/peds.2007-2329C 3718 196 37.3
4 FRAYLING TM, 2007, SCIENCE 10.1126/science.1141634 3706 195 37.2
5 HEDLEY AA, 2004, J AM MED ASSOC 10.1001/jama.291.23.2847 3642 166 30.6
6 WHITAKER RC, 1997, NEW ENGL J MED 10.1056/NEJM199709253371301 3399 117 21.9
7 OGDEN CL, 2002, J AM MED ASSOC 10.1001/jama.288.14.1728 3328 139 20.4
8 OGDEN CL, 2012, J AM MED ASSOC 10.1001/jama.2012.40 3117 223 75.2
9 WEISS R, 2004, NEW ENGL J MED 10.1056/NEJMoa031049 2795 127 23.5
10 WANG Y, 2006, INT J PEDIATR OBES 10.1080/17477160600586747 2128 106 25.7
Corresponding Author's Countries
Country Articles Freq SCP MCP MCP_Ratio
1 USA 3697 0.3411 3239 458 0.1239
2 CHINA 566 0.0522 409 157 0.2774
3 BRAZIL 564 0.0520 459 105 0.1862
4 UNITED KINGDOM 439 0.0405 304 135 0.3075
5 AUSTRALIA 394 0.0363 271 123 0.3122
6 ITALY 394 0.0363 319 75 0.1904
7 CANADA 362 0.0334 280 82 0.2265
8 GERMANY 347 0.0320 240 107 0.3084
9 SPAIN 320 0.0295 227 93 0.2906
10 TURKEY 309 0.0285 299 10 0.0324
SCP: Single Country Publications
MCP: Multiple Country Publications
Total Citations per Country
Country Total Citations Average Article Citations
1 USA 191091 51.69
2 UNITED KINGDOM 34324 78.19
3 AUSTRALIA 15886 40.32
4 GERMANY 15587 44.92
5 CHINA 11835 20.91
6 CANADA 11720 32.38
7 ITALY 10226 25.95
8 BRAZIL 10164 18.02
9 FRANCE 8709 36.90
10 SPAIN 8040 25.12
Most Relevant Sources
Sources Articles
1 INTERNATIONAL JOURNAL OF OBESITY 382
2 PEDIATRIC OBESITY 269
3 OBESITY 261
4 CHILDHOOD OBESITY 221
5 BMC PUBLIC HEALTH 215
6 JOURNAL OF PEDIATRIC ENDOCRINOLOGY AND METABOLISM 198
7 NUTRIENTS 190
8 PLOS ONE 174
9 INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 173
10 PEDIATRICS 150
Most Relevant Keywords
Author Keywords (DE) Articles Keywords-Plus (ID) Articles
1 OBESITY 4850 FEMALE 16486
2 ADOLESCENTS 1606 MALE 15664
3 OVERWEIGHT 1418 ADOLESCENT 15041
4 CHILDHOOD OBESITY 1244 CHILD 14469
5 CHILDREN 1228 OBESITY 13768
6 ADOLESCENT 895 HUMAN 11268
7 BODY MASS INDEX 651 ARTICLE 9382
8 PHYSICAL ACTIVITY 579 HUMANS 9327
9 INSULIN RESISTANCE 416 BODY MASS 6998
10 CHILD 405 CHILDHOOD OBESITY 5905
pedob_bibds %>%
count(PY) %>%
mutate(Gap = case_when(
PY %in% 1994:2003 ~ "1994-2003",
PY %in% 2004:2013 ~ "2004-2013",
PY %in% 2014:2023 ~ "2014-2023"
)) %>%
group_by(Gap) %>%
summarise(n = sum(n), .groups = "drop") %>%
bind_rows(.,
summarise(., Gap = "1994-2023 (total)", n = sum(n)))gmagr_9423 <- pedob_bibds %>%
count(PY) %>%
mutate(AGR = (n - lag(n)) / lag(n) * 100) %>%
filter(!is.na(AGR)) %>%
summarise(geommean_agr = (exp(mean(log(1 + AGR / 100))) - 1) * 100) %>%
pull(geommean_agr)
gmagr_9423[1] 13.56472
gmagr_9403 <- pedob_bibds %>%
count(PY) %>%
filter(PY %in% 1994:2003) %>%
mutate(AGR = (n - lag(n)) / lag(n) * 100) %>%
filter(!is.na(AGR)) %>%
summarise(geommean_agr = (exp(mean(log(1 + AGR / 100))) - 1) * 100) %>%
pull(geommean_agr)
gmagr_9403[1] 21.80082
gmagr_0413 <- pedob_bibds %>%
count(PY) %>%
filter(PY %in% 2004:2013) %>%
mutate(AGR = (n - lag(n)) / lag(n) * 100) %>%
filter(!is.na(AGR)) %>%
summarise(geommean_agr = (exp(mean(log(1 + AGR / 100))) - 1) * 100) %>%
pull(geommean_agr)
gmagr_0413[1] 18.96887
gmagr_1423 <- pedob_bibds %>%
count(PY) %>%
filter(PY %in% 2014:2023) %>%
mutate(AGR = (n - lag(n)) / lag(n) * 100) %>%
filter(!is.na(AGR)) %>%
summarise(geommean_agr = (exp(mean(log(1 + AGR / 100))) - 1) * 100) %>%
pull(geommean_agr)
gmagr_1423[1] 0.9307673
#4682B4 steelblue
#CD5C5C indianred
#2E8B57 seagreen
pedob_bibds %>%
count(PY) %>%
ggplot(aes(x = PY, y = n)) +
geom_vline(xintercept = c(2003.5, 2013.5),
linetype = "dashed", colour = "indianred") + #CD5C5C
geom_col(fill = "seagreen", colour = "black") + #2E8B57
annotate("text", x = 2005, y = 1050,
label = paste0("1994-2023 AGR = ",
sprintf("%.1f", gmagr_9423), "%"),
color = "black", hjust = 0, size = 3) + # 1994-2023
annotate("text", x = 1995, y = 150,
label = paste0("1994-2003 AGR = ",
sprintf("%.1f", gmagr_9403), "%"),
color = "black", hjust = 0, size = 3) + # 1994-2003
annotate("text", x = 2005, y = 850,
label = paste0("2004-2013 AGR = ",
sprintf("%.1f", gmagr_0413), "%"),
color = "black", hjust = 0, size = 3) + # 2004-2013
annotate("text", x = 2015, y = 950,
label = paste0("2014-2023 AGR = ",
sprintf("%.1f", gmagr_1423), "%"),
color = "black", hjust = 0, size = 3) + # 2014-2023
scale_x_continuous(breaks = seq(1986, 2030, 4)) +
scale_y_continuous(breaks = seq(0, 1100, 100)) +
coord_cartesian(ylim = c(0, 1050)) +
labs(x = "Publication Year",
y = "Number of Publications") +
theme_bw()ggsave("production plot.png")pedob_bibds %>%
summarise(total_unique_journals = n_distinct(SO))pedob_bibds %>%
count(SO, sort = T) %>%
slice_max(n, n = 20) %>%
mutate(rank = row_number(), .before = 1)pedob_bibds %>%
filter(PY %in% 1994:2003) %>%
count(SO, sort = TRUE) %>%
slice_max(n, n = 10) %>%
mutate(rank = row_number(), .before = 1)pedob_bibds %>%
filter(PY %in% 2004:2013) %>%
count(SO, sort = TRUE) %>%
slice_max(n, n = 10) %>%
mutate(rank = row_number(), .before = 1)pedob_bibds %>%
filter(PY %in% 2014:2023) %>%
count(SO, sort = TRUE) %>%
slice_max(n, n = 10) %>%
mutate(rank = row_number(), .before = 1)pedob_bibds %>%
mutate(keyword_count = str_count(DE, ";") + 1) %>%
count(keyword_count)#4682B4 steelblue
#CD5C5C indianred
#2E8B57 seagreen
pedob_bibds %>%
mutate(keyword_count = str_count(DE, ";") + 1) %>%
count(keyword_count) %>%
ggplot(aes(x = keyword_count, y = n)) +
geom_col(fill = "#2E8B57", color = "black") + # seagreen
scale_x_continuous(breaks = seq(1, 21, 1)) +
scale_y_continuous(breaks = seq(0, 5000, 500)) +
coord_cartesian(xlim = c(1, 11)) + # there are papers with DE > 15!
labs(title = "Number of Author's Keyword per Articles",
x = "Author's Keywords Count",
y = "Number of Publications") +
theme_bw()debyti <- pedob_bibds %>%
select(TI, PY, DE) %>%
separate_wider_delim(DE, delim = ";", names = paste0("de", 1:10),
too_many = "drop", too_few = "align_start") %>%
pivot_longer(cols = starts_with("de"),
names_to = "de_position",
values_to = "de_aukw",
values_drop_na = T) %>%
mutate(de_aukw = str_trim(de_aukw),
de_aukw = str_to_upper(de_aukw),
de_aukw = str_replace_all(de_aukw, "\\s+", " "),
de_aukw = str_replace_all(de_aukw, "-", " "),
de_aukw = stri_trans_general(de_aukw, "Latin-ASCII") )
debytidebyti %>%
count(de_aukw, sort = T) debyti %>%
filter(PY %in% 1994:2003) %>%
count(de_aukw, sort = T) debyti %>%
filter(PY %in% 2004:2013) %>%
count(de_aukw, sort = T) debyti %>%
filter(PY %in% 2014:2023) %>%
count(de_aukw, sort = T)